17 papers
Explaining Object Detectors via Collective Contribution of Pixels
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Visual explanations for object detectors are crucial for enhancing their reliability. Object detectors identify and localize instances by assessing multiple visual features collect…
Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. Howe…
Zero-Shot Textual Explanations via Translating Decision-Critical Features
Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto
Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but…
Guided Diffusion Sampling for Precipitation Forecast Interventions
Ayumu Ueyama, Kazuhiko Kawamoto, Hiroshi Kera
Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. However, to the best of our knowle…
Learning Large-Scale Modular Addition with an Auxiliary Modulus
Hanato Kikuchi, Ryosuke Masuya, Kazuhiko Kawamoto +1
Learning parity functions, more general modular addition, is a challenging machine learning task due to its input sensitivity. A recent study substantially scaled modular addition…
Discovering Learning-Friendly Generation Orders for Sequential Computation
Yuta Sato, Kazuhiko Kawamoto, Hiroshi Kera
Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds.…